vectorless-qv 0.2.1

Reasoning-based RAG for Excel financial models — no vectors, no chunking. Supports all major LLM providers.

Vectorless-QV

Reasoning-based RAG for Excel financial models — no vectors, no chunking.

Inspired by the PageIndex architecture, Vectorless builds a hierarchical tree index of an Excel workbook and uses an LLM reasoning loop to navigate it — just like a financial analyst would.

Supports all major LLM providers: AWS Bedrock, OpenAI, Anthropic, Google Gemini, Azure OpenAI, Ollama (local), Groq, and Together AI.

Features

• No vector database — no embeddings, no similarity search
• No chunking — formulas and cell relationships stay intact
• Hierarchical tree index — sheets → tables → formulas → cells
• LLM-driven reasoning — parallel tool calls, search, drill-down
• Formula tracing — follows =+PL!X118 across sheets
• What-if analysis — override cells and recalculate formulas
• 100% traceable — every answer cites exact sheet, cell, and formula
• Multi-provider LLM support — swap providers with a single flag

Installation

pip install vectorless-qv

Install with the LLM provider(s) you need:

pip install vectorless-qv[bedrock]     # AWS Bedrock (Claude, Titan, Llama, Mistral)
pip install vectorless-qv[openai]      # OpenAI (GPT-4o, o1, o3)
pip install vectorless-qv[anthropic]   # Anthropic direct API (Claude)
pip install vectorless-qv[google]      # Google Gemini
pip install vectorless-qv[azure]       # Azure OpenAI
pip install vectorless-qv[ollama]      # Ollama local models
pip install vectorless-qv[groq]        # Groq Cloud
pip install vectorless-qv[together]    # Together AI
pip install vectorless-qv[all]         # All providers

Quick Start

1. Index a workbook

vectorless-qv index --file financials.xlsx

This creates two files:

• financials.tree.json — the hierarchical tree index
• financials.parsed.json — raw cell data for query-time lookups

2. Ask questions

# Single question (default: AWS Bedrock)
vectorless-qv query --file financials.xlsx -q "What is the gross margin?"

# Use a different provider
vectorless-qv query --file financials.xlsx --provider openai -q "What is the gross margin?"

# Use a specific model
vectorless-qv query --file financials.xlsx --provider anthropic --model claude-opus-4-20250514 -q "..."

# Local model via Ollama
vectorless-qv query --file financials.xlsx --provider ollama --model llama3.1 -q "..."

# Interactive mode
vectorless-qv query --file financials.xlsx --provider openai

# With reasoning trace
vectorless-qv query --file financials.xlsx -q "How is EBITDA calculated?" -v

3. Discover providers and models

# List all providers
vectorless-qv list-providers

# Show models for a specific provider
vectorless-qv list-providers --provider openai

4. Inspect the tree

# Full overview
vectorless-qv inspect --file financials.xlsx

# Specific node
vectorless-qv inspect --file financials.xlsx --node s1_t0

Python API

from vectorless_qv import parse_workbook, build_tree, VectorlessAgent

# Parse and index
data = parse_workbook("financials.xlsx")
tree = build_tree(data)

# Query with any provider
agent = VectorlessAgent(tree=tree, workbook_data=data, excel_path="financials.xlsx",
                        provider="openai", model_id="gpt-4o")
result = agent.query("What drives net income?")
print(result["answer"])
print(result["citations"])

# Switch to local Ollama
agent = VectorlessAgent(tree=tree, workbook_data=data, excel_path="financials.xlsx",
                        provider="ollama", model_id="llama3.1")

# Or use Bedrock (default)
agent = VectorlessAgent(tree=tree, workbook_data=data, excel_path="financials.xlsx")

# List available providers programmatically
from vectorless_qv import list_providers
for p in list_providers():
    print(f"{p['name']}: {p['default_model']} ({len(p['models'])} models)")

Note: BedrockAgent is still available as a backward-compatible alias for VectorlessAgent.

Supported Providers

Provider	Install	Default Model	Env Variable
bedrock	pip install vectorless-qv[bedrock]	global.anthropic.claude-sonnet-4-6	AWS_DEFAULT_REGION, AWS_ACCESS_KEY_ID
openai	pip install vectorless-qv[openai]	gpt-4o	OPENAI_API_KEY
anthropic	pip install vectorless-qv[anthropic]	claude-sonnet-4-20250514	ANTHROPIC_API_KEY
google	pip install vectorless-qv[google]	gemini-2.0-flash	GOOGLE_API_KEY
azure	pip install vectorless-qv[azure]	gpt-4o	AZURE_OPENAI_API_KEY, AZURE_OPENAI_ENDPOINT
ollama	pip install vectorless-qv[ollama]	llama3.1	OLLAMA_BASE_URL (default: localhost:11434)
groq	pip install vectorless-qv[groq]	llama-3.3-70b-versatile	GROQ_API_KEY
together	pip install vectorless-qv[together]	Llama-3.3-70B-Instruct-Turbo	TOGETHER_API_KEY

Architecture

Excel File
    │
    ▼
┌──────────┐     ┌──────────┐     ┌──────────┐
│  Parser  │────▶│ Indexer   │────▶│ Tree JSON│
│(openpyxl)│     │(hierarchy)│     │  (ToC)   │
└──────────┘     └──────────┘     └──────────┘
                                       │
                                       ▼
                               ┌───────────────┐
                               │VectorlessAgent│◀── User Question
                               │ (any LLM)     │
                               └──────┬────────┘
                                      │
                    ┌─────────────────┼─────────────────┐
                    ▼                 ▼                 ▼
              drill_down         get_cells         search_rows
              get_row            what_if            answer
                                      │
                    ┌─────────────────┼─────────────────┐
                    ▼                 ▼                 ▼
                Bedrock           OpenAI            Ollama
                Anthropic         Google            Groq
                Azure             Together          ...

License

MIT